© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73996
    Prev
    Next
    INDEX
    Explanations

    dates, numbers, and ordinal numbers

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron selectively activates on numeric tokens (digits or numbers), including dates, statistics, and other numeric values.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     restante
    -0.76
     restantes
    -0.74
    Karen
    -0.73
    痊
    -0.72
     Finished
    -0.71
    finished
    -0.70
     Skeleton
    -0.70
     spécialement
    -0.69
    write
    -0.69
    dération
    -0.68
    POSITIVE LOGITS
     initial
    1.22
     initially
    1.09
     previous
    1.08
     тогда
    1.02
     awalnya
    0.99
     then
    0.93
     Initially
    0.93
     damaligen
    0.93
    当时
    0.92
     sebelumnya
    0.92
    Activations Density 0.059%

    No Known Activations